{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H3UKIKZ4QUTQURAIGCX5356BOD","short_pith_number":"pith:H3UKIKZ4","canonical_record":{"source":{"id":"1806.03431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-09T07:40:38Z","cross_cats_sorted":[],"title_canon_sha256":"d89d8d40bab4b5d01fc05f9b10c4fcedfc5d5c558cde997deff2aa700e1feea9","abstract_canon_sha256":"adf2a6c84fde672f28d9a96fe4d35e733dd70b9cdd0c409e257c629136408616"},"schema_version":"1.0"},"canonical_sha256":"3ee8a42b3c85270a440830afddf7c170c82c55835350f089651de1a749bfee96","source":{"kind":"arxiv","id":"1806.03431","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03431","created_at":"2026-05-18T00:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03431v1","created_at":"2026-05-18T00:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03431","created_at":"2026-05-18T00:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"H3UKIKZ4QUTQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H3UKIKZ4QUTQURAI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H3UKIKZ4","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H3UKIKZ4QUTQURAIGCX5356BOD","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-09T07:40:38Z","cross_cats_sorted":[],"title_canon_sha256":"d89d8d40bab4b5d01fc05f9b10c4fcedfc5d5c558cde997deff2aa700e1feea9","abstract_canon_sha256":"adf2a6c84fde672f28d9a96fe4d35e733dd70b9cdd0c409e257c629136408616"},"schema_version":"1.0"},"canonical_sha256":"3ee8a42b3c85270a440830afddf7c170c82c55835350f089651de1a749bfee96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:43.415696Z","signature_b64":"1PxRJf33UlM2iguRF6bbiunDExVElkiJuQbb5qAkGumqdusJ8x4xrMT31lQsfP+siFwmiQTzR0T+sqgCw+MhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee8a42b3c85270a440830afddf7c170c82c55835350f089651de1a749bfee96","last_reissued_at":"2026-05-18T00:13:43.415047Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:43.415047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03431","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQlHsNVLWYfbqqz7mAe59q1aJdO1lvIRheFZMt6Kfe6WfqYv3jFdtYPh+QfNMxZNfYL+euKpDXi+8/gpszKwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T17:11:47.841127Z"},"content_sha256":"dbe4bd19e7fac578e717ffcee6672490ae5e2c231ce8461c39fb10162f085e4a","schema_version":"1.0","event_id":"sha256:dbe4bd19e7fac578e717ffcee6672490ae5e2c231ce8461c39fb10162f085e4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H3UKIKZ4QUTQURAIGCX5356BOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Familiarity and Frequency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hiroshi Terada, Kumiko Tanaka-Ishii","submitted_at":"2018-06-09T07:40:38Z","abstract_excerpt":"Word frequency is assumed to correlate with word familiarity, but the strength of this correlation has not been thoroughly investigated. In this paper, we report on our analysis of the correlation between a word familiarity rating list obtained through a psycholinguistic experiment and the log-frequency obtained from various corpora of different kinds and sizes (up to the terabyte scale) for English and Japanese. Major findings are threefold: First, for a given corpus, familiarity is necessary for a word to achieve high frequency, but familiar words are not necessarily frequent. Second, correl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03431","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxL4ZKtk3TGIf+vGO8bA3D5fIwDrUm6NpRsqJkojJ/hi67cO3KERwyZ7dludd3oU3YVNEZnddL4eqKm7hD7qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T17:11:47.860351Z"},"content_sha256":"2abc2188919735fbafc1289e1a40bc4196d9221b89b02296c9d661d6b1ab4144","schema_version":"1.0","event_id":"sha256:2abc2188919735fbafc1289e1a40bc4196d9221b89b02296c9d661d6b1ab4144"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3UKIKZ4QUTQURAIGCX5356BOD/bundle.json","state_url":"https://pith.science/pith/H3UKIKZ4QUTQURAIGCX5356BOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3UKIKZ4QUTQURAIGCX5356BOD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T17:11:47Z","links":{"resolver":"https://pith.science/pith/H3UKIKZ4QUTQURAIGCX5356BOD","bundle":"https://pith.science/pith/H3UKIKZ4QUTQURAIGCX5356BOD/bundle.json","state":"https://pith.science/pith/H3UKIKZ4QUTQURAIGCX5356BOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3UKIKZ4QUTQURAIGCX5356BOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H3UKIKZ4QUTQURAIGCX5356BOD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"adf2a6c84fde672f28d9a96fe4d35e733dd70b9cdd0c409e257c629136408616","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-09T07:40:38Z","title_canon_sha256":"d89d8d40bab4b5d01fc05f9b10c4fcedfc5d5c558cde997deff2aa700e1feea9"},"schema_version":"1.0","source":{"id":"1806.03431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03431","created_at":"2026-05-18T00:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03431v1","created_at":"2026-05-18T00:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03431","created_at":"2026-05-18T00:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"H3UKIKZ4QUTQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H3UKIKZ4QUTQURAI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H3UKIKZ4","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:2abc2188919735fbafc1289e1a40bc4196d9221b89b02296c9d661d6b1ab4144","target":"graph","created_at":"2026-05-18T00:13:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Word frequency is assumed to correlate with word familiarity, but the strength of this correlation has not been thoroughly investigated. In this paper, we report on our analysis of the correlation between a word familiarity rating list obtained through a psycholinguistic experiment and the log-frequency obtained from various corpora of different kinds and sizes (up to the terabyte scale) for English and Japanese. Major findings are threefold: First, for a given corpus, familiarity is necessary for a word to achieve high frequency, but familiar words are not necessarily frequent. Second, correl","authors_text":"Hiroshi Terada, Kumiko Tanaka-Ishii","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-09T07:40:38Z","title":"Word Familiarity and Frequency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03431","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dbe4bd19e7fac578e717ffcee6672490ae5e2c231ce8461c39fb10162f085e4a","target":"record","created_at":"2026-05-18T00:13:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"adf2a6c84fde672f28d9a96fe4d35e733dd70b9cdd0c409e257c629136408616","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-09T07:40:38Z","title_canon_sha256":"d89d8d40bab4b5d01fc05f9b10c4fcedfc5d5c558cde997deff2aa700e1feea9"},"schema_version":"1.0","source":{"id":"1806.03431","kind":"arxiv","version":1}},"canonical_sha256":"3ee8a42b3c85270a440830afddf7c170c82c55835350f089651de1a749bfee96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ee8a42b3c85270a440830afddf7c170c82c55835350f089651de1a749bfee96","first_computed_at":"2026-05-18T00:13:43.415047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:43.415047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1PxRJf33UlM2iguRF6bbiunDExVElkiJuQbb5qAkGumqdusJ8x4xrMT31lQsfP+siFwmiQTzR0T+sqgCw+MhAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:43.415696Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbe4bd19e7fac578e717ffcee6672490ae5e2c231ce8461c39fb10162f085e4a","sha256:2abc2188919735fbafc1289e1a40bc4196d9221b89b02296c9d661d6b1ab4144"],"state_sha256":"929ec477779295e7aa006e472d06f930e0e08f2dafdcc572f46340cdcde4eab7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kFM3YbbcMNyK1D3CUCk+rS77Dz++A1n/zWyYwjeFykPDC76zEVTVboGPMKIUAZ8rus7z8mWxNsWpObasZb0RCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T17:11:47.899805Z","bundle_sha256":"bdc1426f4ce7ad086d7c3b62d7a832d9642fc01774532517b9c925f497b2f464"}}